Journal of Electrical Systems and Information Technology

Table 2 CNN and LSTM parameters and performance for \({W}_{x}\) forecasting

From: A novel technique for forecasting the optimal production of a wind generator installed at any geographical point located within a very large area

CNN parameters		LSTM parameters
INPUT_WIDTH: 18 h
LABEL_WIDTH: 12 h
Filters	70	Units	460
Units	590
Learning_rates	\({10}^{-3}\)	Learning_rates:	\({10}^{-3}\)
RMSE	0.62 m/s	RMSE	0.43 m/s
R²	83%	R²	85%

Back to article page